AI AGENTS
Fact-check guest and inbound blog submissions on intake
When a draft arrives by email, an agent verifies its factual claims against sources and replies to the author with a pass/revise verdict plus the exact claims that need a citation.
How it runs
The automated pipeline, trigger to output.
- TriggerNew draft email to submissions inboxGmail
- ActionExtract draft text and itemize claimsOpenAI
- ActionSearch for supporting primary sourcesBrave Search
- LogicAll claims sourced, or gaps found?
- OutputReply to author with verdict and required citationsGmail
What it does
Guest posts and agency drafts arrive full of confident assertions and zero footnotes. This agent intercepts each inbound draft by email, extracts its claims, searches for supporting primary sources, and emails the author back a structured verdict: which claims are sourced, which need a citation, and which appear false — turning a vague "we'll review it" into a concrete revision list.
When to use it
For editorial teams accepting external contributions who want a consistent first-pass factual screen before a human editor spends time on a piece.
How it works
- 1A new email to the submissions inbox triggers the run.
- 2The agent extracts the draft text from the message body or attachment.
- 3OpenAI itemizes the factual claims in the draft.
- 4It searches Brave Search for supporting sources and reads the strongest results.
- 5A branch decides pass (all claims sourced) versus revise (gaps or contradictions).
- 6A reply email goes to the author with the verdict and the specific claims requiring citations.
Set it up
What you configure once, before turning it on.
- 1Connect GmailRead, draft, send, label.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect Brave SearchWeb, news, image, video search.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More AI Agents workflows
Custom Metrics Cardinality Spike Pager
A webhook from a Datadog monitor fires when custom-metric cardinality jumps; an agent pinpoints the offending metric and tag, estimates the added cost.
Sentry-to-Confluence Runbook Updater
When a Sentry issue is resolved, the agent finds the matching Confluence runbook page and proposes an inline update with the verified fix.
Stale Doc-PR Chaser for Runbook Gaps
On a daily schedule the agent finds runbook doc PRs that were opened from resolved incidents but never reviewed, summarizes what each one fixes.
Resolved Incident to Public Troubleshooting Doc
For customer-facing errors resolved in Sentry, the agent drafts a sanitized troubleshooting entry and opens a PR to your ReadMe documentation.
On-Call Runbook Gap Closer: Resolved Sentry Issues to Doc PRs
An agent reads each newly resolved Sentry issue, compares the actual fix against your existing runbook, and opens a GitHub PR adding the missing remediation steps.
Weekly On-Call Doc-Gap Digest
Each week the agent reviews every Sentry issue resolved in the last 7 days, ranks the ones whose runbook coverage is missing or thin.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.